|
| 1 | +#!/usr/bin/env python |
| 2 | + |
| 3 | +""" I honestly don't even know how the hell this works, just use it. """ |
| 4 | +__author__ = "Scott Stamp <[email protected]>" |
| 5 | + |
| 6 | +from HTMLParser import HTMLParser |
| 7 | +from urlparse import urljoin |
| 8 | +from sys import setrecursionlimit |
| 9 | +import re |
| 10 | +import requests |
| 11 | + |
| 12 | +setrecursionlimit(10000) |
| 13 | +root = 'http://localhost:8000' |
| 14 | + |
| 15 | + |
| 16 | +class DataHolder: |
| 17 | + |
| 18 | + def __init__(self, value=None, attr_name='value'): |
| 19 | + self._attr_name = attr_name |
| 20 | + self.set(value) |
| 21 | + |
| 22 | + def __call__(self, value): |
| 23 | + return self.set(value) |
| 24 | + |
| 25 | + def set(self, value): |
| 26 | + setattr(self, self._attr_name, value) |
| 27 | + return value |
| 28 | + |
| 29 | + def get(self): |
| 30 | + return getattr(self, self._attr_name) |
| 31 | + |
| 32 | + |
| 33 | +class Parser(HTMLParser): |
| 34 | + global root |
| 35 | + |
| 36 | + ids = set() |
| 37 | + crawled = set() |
| 38 | + anchors = {} |
| 39 | + pages = set() |
| 40 | + save_match = DataHolder(attr_name='match') |
| 41 | + |
| 42 | + def __init__(self, origin): |
| 43 | + self.origin = origin |
| 44 | + HTMLParser.__init__(self) |
| 45 | + |
| 46 | + def handle_starttag(self, tag, attrs): |
| 47 | + attrs = dict(attrs) |
| 48 | + if 'href' in attrs: |
| 49 | + href = attrs['href'] |
| 50 | + |
| 51 | + if re.match('^{0}|\/|\#[\S]{{1,}}'.format(root), href): |
| 52 | + if self.save_match(re.search('.*\#(.*?)$', href)): |
| 53 | + if self.origin not in self.anchors: |
| 54 | + self.anchors[self.origin] = set() |
| 55 | + self.anchors[self.origin].add( |
| 56 | + self.save_match.match.groups(1)[0]) |
| 57 | + |
| 58 | + url = urljoin(root, href) |
| 59 | + |
| 60 | + if url not in self.crawled and not re.match('^\#', href): |
| 61 | + self.crawled.add(url) |
| 62 | + Parser(url).feed(requests.get(url).content) |
| 63 | + |
| 64 | + if 'id' in attrs: |
| 65 | + self.ids.add(attrs['id']) |
| 66 | + # explicit <a name=""></a> references |
| 67 | + if 'name' in attrs: |
| 68 | + self.ids.add(attrs['name']) |
| 69 | + |
| 70 | + |
| 71 | +r = requests.get(root) |
| 72 | +parser = Parser(root) |
| 73 | +parser.feed(r.content) |
| 74 | +for anchor in sorted(parser.anchors): |
| 75 | + if not re.match('.*/\#.*', anchor): |
| 76 | + for anchor_name in parser.anchors[anchor]: |
| 77 | + if anchor_name not in parser.ids: |
| 78 | + print 'Missing - ({0}): #{1}'.format( |
| 79 | + anchor.replace(root, ''), anchor_name) |
0 commit comments